haixuanTao
d2113d7b50
Add reinstall command within run.rs to avoid silently using old version of dora node api python
1 year ago
haixuanTao
8b19716b3e
Fix pip installation of development dora node api python
1 year ago
haixuantao
649902783c
Fix CI/CD
1 year ago
haixuantao
0cd764980d
migrate example to uv to make it independant of virtual environment activation
1 year ago
haixuantao
2d12aa0f94
Fix kokoro demo with gguf based inference of qwen2.5 0.5B
1 year ago
haixuantao
35e72cbc15
Add latest news section and improve readme initial section
1 year ago
haixuantao
aa32c2483f
Adding speech to speech example within vlm
1 year ago
haixuantao
8358e3a0f9
fix outetts pyproject issue with metal flag for llama-cpp-python
1 year ago
haixuantao
7da62f3a88
Adding text to speech into qwenvl demo
1 year ago
haixuantao
65135134c7
Add dora-qwen2-5-vl
1 year ago
haixuantao
036c9fa93c
Improve README on examples
1 year ago
haixuantao
d3ac0a3d33
Improve `README` and create 2 dataflow, one for dev and one for full remote version
1 year ago
haixuantao
fc8bc8a4fe
Improve vlm by adding speech to text within example
1 year ago
haixuantao
90a71b8e1d
Make VLM macos compatible
1 year ago
haixuanTao
c08fe0f3aa
Fix small example issues
1 year ago
Haixuan Xavier Tao
a90221d70b
Temporary fix qwenvl2 queue error ( #688 )
In order to get the best performance from Qwenvl2, we need to temporary
add this piece of code that is going to unqueue qwenvl queue.
This is directly linked to: https://github.com/dora-rs/dora/pull/652
which is that we currently having a queue issue within nodes for
`queue_size: 1` where the queue is actually pending older data and not
the newest one.
1 year ago
haixuanTao
9133406c18
Add `README` section for rerun within the dataflow
1 year ago
haixuanTao
edc1467612
Add next call loop in qwenvl2 to queue fix
1 year ago
haixuanTao
e1742f9ee2
Adding tick within the VLM example
1 year ago
haixuanTao
ab77fb8874
Adding qwenvl2 and its data recorder
1 year ago